[ovs-discuss] discuss Digest, Vol 107, Issue 23

[Mrityunjay Kumar]

Ju

On Tue, 8 May 2018, 17:31 , <ovs-discuss-request at openvswitch.org> wrote:

> Send discuss mailing list submissions to
>         ovs-discuss at openvswitch.org
>
> To subscribe or unsubscribe via the World Wide Web, visit
>         https://mail.openvswitch.org/mailman/listinfo/ovs-discuss
> or, via email, send a message with subject or body 'help' to
>         ovs-discuss-request at openvswitch.org
>
> You can reach the person managing the list at
>         ovs-discuss-owner at openvswitch.org
>
> When replying, please edit your Subject line so it is more specific
> than "Re: Contents of discuss digest..."
>
>
> Today's Topics:
>
>    1. Re: Multiple dpdk-netdev datapath with OVS 2.9
>       (Raymond Burkholder)
>
>
> ----------------------------------------------------------------------
>
> Message: 1
> Date: Mon, 7 May 2018 22:38:45 -0300
> From: Raymond Burkholder <ray at oneunified.net>
> To: ovs-discuss at openvswitch.org
> Subject: Re: [ovs-discuss] Multiple dpdk-netdev datapath with OVS 2.9
> Message-ID: <af55ec12-e756-b4e6-35f2-605373765096 at oneunified.net>
> Content-Type: text/plain; charset=utf-8; format=flowed
>
> On 05/07/2018 01:41 PM, alp.arslan at xflowresearch.com wrote:
> > What would you recommend as a controller, also would adding rules using a
> > controller be faster than "ovs-ofctl"? My application continuously add
> and
> > delete flows based on the traffic patterns, and it works fine if there
> is no
> > traffic flowing through the OVS, but as soon as I turn on the 40 G links,
> > the time to apply the rules starting hitting several seconds sometimes
> up to
> > 100s. It keeps increasing as the existing number of flows increase.
>
> Wouldn't it be better to run some sort of analysis to determine at what
> point your flow insertions start to fall behind?  Are you setting up
> many short lived flows?  Do you have jumbo flows?  Or some mixture?
>
> Then figure out how many flows adjustments you need from testing.
>
> Linux should be able to handle 10G.  40G, without a bunch of tuning and
> analysis and distribution, could be challenging.  And depends upon what
> stuff is being off-loaded, and what is calculated locally.
>
> At that point, you have choices:
>
> Ryu: python based controller with an established support base, but might
> be slow for your needs
>
> Some Java based engines:  compiled and used by some bigger boys
>
> Come C++ engines:  fast code, and maybe fast insertions (c++ and java
> would send messages which might bypass some of the ovs-ofctl parsing)
>
> Some people diddle with certain functions directly (see past archives
> for several mentions)
>
> Or maybe use P4 or eBPF to handle your packet handling?
>
> >
> > Can an SDN controller solve this issue? Or is it an inherent OVS
> limitation
> > where it takes more time to add rules if more packets are going to the OF
> > classifier?
> >
>
> --
> Raymond Burkholder
> ray at oneunified.net
> https://blog.raymond.burkholder.net
>
> --
> This message has been scanned for viruses and
> dangerous content by MailScanner, and is
> believed to be clean.
>
>
>
> ------------------------------
>
> _______________________________________________
> discuss mailing list
> discuss at openvswitch.org
> https://mail.openvswitch.org/mailman/listinfo/ovs-discuss
>
>
> End of discuss Digest, Vol 107, Issue 23
> ****************************************
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mail.openvswitch.org/pipermail/ovs-discuss/attachments/20180508/06df1fb2/attachment.html>